INDEX

Explanations

terms related to washing and cleanliness

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð»Ð¸Ð½Ð¸

-0.16

athe

-0.15

chai

-0.15

iem

-0.15

ials

-0.14

acon

-0.14

zan

-0.14

iate

-0.14

cks

-0.13

aptcha

-0.13

POSITIVE LOGITS

ngo

0.17

 Chew

0.15

onian

0.15

emy

0.15

lien

0.15

icz

0.14

 Nicola

0.14

ARB

0.14

ebb

0.14

ingt

0.14

Activations Density 0.027%

terms related to washing and cleanliness

No Comments

No Known Activations